WO2020172073A1 - Analyse de données d'image pour déterminer des informations d'échantillon rectal - Google Patents

Analyse de données d'image pour déterminer des informations d'échantillon rectal Download PDF

Info

Publication number
WO2020172073A1
WO2020172073A1 PCT/US2020/018390 US2020018390W WO2020172073A1 WO 2020172073 A1 WO2020172073 A1 WO 2020172073A1 US 2020018390 W US2020018390 W US 2020018390W WO 2020172073 A1 WO2020172073 A1 WO 2020172073A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
rectal sample
rectal
liquid
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/US2020/018390
Other languages
English (en)
Inventor
Simon C. MATHEWS
Amit Banerjee
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Johns Hopkins University
Original Assignee
Johns Hopkins University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Johns Hopkins University filed Critical Johns Hopkins University
Priority to US17/310,686 priority Critical patent/US12118725B2/en
Publication of WO2020172073A1 publication Critical patent/WO2020172073A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture

Definitions

  • a colonoscopy is an endoscopic procedure that is commonly used to screen for colorectal cancer or to detect other abnormalities in the large intestine and rectum.
  • a patient consumes a bowel preparation agent to cleanse the bowel before undergoing a colonoscopy.
  • a clean bowel aids an endoscopist’s ability to visualize colonic mucosa.
  • a method may include obtaining, by a device, a first image of a liquid in a receptacle; analyzing, by the device, the first image to determine a first set of visual characteristics concerning the liquid; obtaining, by the device, a second image of a rectal sample in the liquid in the receptacle, wherein the rectal sample originated from a bowel of a subject; analyzing, by the device, the second image to determine a second set of visual characteristics concerning the rectal sample; determining, by the device and based on the first set of visual characteristics and the second set of visual characteristics, rectal sample information; and causing, by the device, one or more actions to be performed based on the rectal sample information.
  • a device may include one or more memories, and one or more processors, communicatively coupled to the one or more memories, configured to:
  • a user device obtains, from a user device, a first image of a liquid in a receptacle; analyze the first image to determine a characteristic associated with the liquid; obtain, from the user device, a second image of a rectal sample in the liquid in the receptacle; analyze the second image to determine a characteristic associated with the rectal sample; determine, using one or more machine learning models and based on the characteristic associated with the liquid and the characteristic associated with the rectal sample, rectal sample information; and cause one or more actions to be performed based on the rectal sample information.
  • a non-transitory computer-readable medium may store one or more instructions.
  • the one or more instructions when executed by one or more processors of a user device, may cause the one or more processors to: cause display, on a display of the user device, of a first instruction regarding capturing an image of a liquid in a receptacle; obtain, after causing display of the first instruction, a first image of the liquid; analyze the first image to determine a first set of characteristics concerning the liquid; cause display, on the display of the user device, of a second instruction regarding capturing an image of a rectal sample, of a user of the user device, in the liquid in the receptacle; obtain, after causing display of the second instruction, a second image of the rectal sample; analyze the second image to determine a second set of characteristics concerning the rectal sample; determine, based on the first set of characteristics and the second set of characteristics, rectal sample information; and automatically perform one or more actions based on the rectal sample information.
  • FIGs. 1A-1D are diagrams of example implementations described herein.
  • FIG. 2 is a diagram of an example environment in which systems and/or methods, described herein, may be implemented.
  • Fig. 3 is a diagram of example components of one or more devices of Fig. 2.
  • FIGs. 4-6 are flowcharts of example processes for analyzing image data to determine rectal sample information.
  • a colonoscopy is an endoscopic procedure commonly used to screen for colorectal cancer or to detect other abnormalities in the colon of a patient.
  • a patient consumes a bowel preparation agent to cleanse the patient’s bowel before undergoing a colonoscopy.
  • a clean bowel aids an endoscopist’s ability to visualize colonic mucosa while performing the colonoscopy.
  • a predictor of colonoscopy quality e.g., whether the endoscopist is able to identify and diagnose lesions in the bowel
  • is the quality of bowel preparation e.g., how well bowel is cleaned so that colonic mucosa can be visualized).
  • the quality of bowel preparation is poor (e.g., the bowel is not sufficiently clean for the endoscopist to visualize the colonic mucosa).
  • the colonoscopy is considered inadequate and commonly results in longer procedure time, increased risk to patients, decreased quality, and/or an incomplete examination. As a result, the procedure frequently needs to be repeated.
  • a device associated with scheduling colonoscopy appointments unnecessarily uses resources (e.g., processing resources, memory resources, power resources, communication resources, and/or the like) to schedule an additional colonoscopy at a later time.
  • resources e.g., processing resources, memory resources, communication resources, and/or the like
  • associated with facilitating imaging of the patient’s colon may be unnecessarily used for a colonoscopy that needs to be redone.
  • resources may be unnecessarily used to facilitate cleaning and sterilizing of colonoscopy tools and equipment (e.g., a colonoscope, cleaning solution, tubing, and/or the like) for a colonoscopy that needs to be redone.
  • colonoscopy tools and equipment e.g., a colonoscope, cleaning solution, tubing, and/or the like
  • a user device and/or an analyzing platform obtains a first image of a liquid in a receptacle (e.g., water in a toilet) and analyzes the first image to determine a first set of visual characteristics concerning the liquid.
  • a receptacle e.g., water in a toilet
  • the user device and/or analyzing platform obtains a second image of a rectal sample (e.g., of the user) in the liquid in the receptacle (e.g., a rectal effluent, a rectal discharge, stool, and/or the like in the water in the toilet) and analyzes the second image to determine a second set of visual characteristics concerning the rectal sample.
  • the user device and/or the analyzing platform determines, based on the first set of visual characteristics and the second set of visual characteristics, rectal sample information.
  • the user device and/or the analyzing platform may determine one or more estimated biochemical measurements associated with the rectal sample, a turbidity score of the rectal sample, information concerning estimated bowel cleanliness of the bowel of the user, and/or the like.
  • the user device and/or the analyzing platform causes, based on the rectal sample information, one or more actions to be performed, such as scheduling a time for a colonoscopy, a physical examination, a blood test, and/or the like; causing display on a display of the user device of an instruction regarding consumption of a bowel preparation agent by the user; and/or the like.
  • the user device and/or the analyzing platform mitigates unnecessary use of resources associated with scheduling and performing the colonoscopy.
  • the user device and/or the analyzing platform may increase a likelihood that the quality of bowel preparation of the user is good, which increases a likelihood that the endoscopist can visualize colonic mucosa in the user’s colon and identify abnormal findings.
  • This increases a likelihood that a colonoscopy will be successfully performed without having to perform another colonoscopy on the user prematurely.
  • device resources e.g., processing resources, memory resources, power resources, communication resources, and/or the like
  • imaging resources e.g., processing resources, memory resources, power resources, communication resources, and/or the like
  • cleaning and sterilizing resources will not be wasted on a colonoscopy that needs to be redone.
  • the user device and/or the analyzing platform may be able to determine an estimated health condition of the user (e.g., that indicates whether the user has a gastrointestinal disease, whether the user is at risk of developing a gastrointestinal disease, whether the user is anemic, whether the user is dehydrated, and/or the like), which may assist in determining a course of treatment for the user. Accordingly, resources, such as device resources for scheduling tests, analyzing test results, and/or the like, that would have been used to otherwise determine the estimated health condition of the user can be conserved.
  • Figs. 1A-1D are diagrams of example implementations 100 described herein.
  • example implementation 100 may include a user device and/or an analyzing platform.
  • the user device may be a communication and/or computing device, such as a mobile phone, a smartphone, a laptop computer, a tablet computer, a smart toilet seat (e.g., a toilet seat device with capabilities to obtain and/or analyze images of rectal samples, as described herein), and/or the like.
  • the user device may include a camera device (e g., one or more cameras) configured to capture images.
  • the camera device of the user device may support one or more image resolutions.
  • An image resolution may be represented as a number of pixel columns (width) and a number of pixel rows (height), such as 1280x720, 1920x1080, 2592x1458, 3840x2160, 4128x2322, 5248x2952, 5312x2988, and/or the like, where higher numbers of pixel columns and higher numbers of pixel rows are associated with higher image resolutions.
  • the user device may include one or more applications (e.g., provided by, or associated with, an entity, such as a health care provider (e.g., a hospital, a doctor’s group, and/or the like)) capable of facilitating image capturing.
  • a user of the user device may activate the one or more applications on the user device (e.g., cause the one or more applications to ran on the user device) to capture an image.
  • the camera device may be configured to capture hyperspectral images (e.g., images associated with infrared light, visible light, ultraviolet, and/or the like).
  • the camera device may include a filter (e.g., a bandpass filter) that is configured to allow the camera device to capture images associated with a particular spectral range (e.g., images associated with red light, green light, blue light, visible light, infrared light, ultraviolet light, and/or the like).
  • the user device may be configured to filter images obtained by the camera device (e.g., using the one or more applications) to allow the user device to modify the images (e.g., to cause the images to include only image data associated with a particular spectral range).
  • the analyzing platform may be a computing device, a server device, a cloud computing device, and/or the like.
  • the user device and/or the analyzing platform may be connected via a network, such as a wired network (e.g., the Internet or another data network), a wireless network (e.g., a wireless local area network, a wireless wide area network, a cellular network, etc ), and/or the like.
  • a network such as a wired network (e.g., the Internet or another data network), a wireless network (e.g., a wireless local area network, a wireless wide area network, a cellular network, etc ), and/or the like.
  • Some example implementations described herein concern a single user device communicating with a single analyzing platform.
  • a plurality of user devices may communicate with one or more analyzing platforms.
  • one or more functions of the analyzing platform may be performed by the user device instead of, or in addition to, being performed by the analyzing platform.
  • one or more functions of the user device may be performed by the analyzing platform instead of, or in addition to, being performed by the user device.
  • the user device may obtain user information relating to the user (e.g., a subject whose rectal sample will be analyzed, as described herein). For example, the user may interact, via a user interface of the user device, with the one or more applications running on the user device to enter the user information into the user device. As another example, the user device may communicate with a different device, such as a server device, to obtain the user information.
  • a server device such as a server device
  • the user information may include an age of the user, a sex of the user, a health status of the user, a health history of the user, information concerning medication consumed by the user, information concerning a bowel preparation agent prescribed for the user (e.g., to cleanse the bowel of the user for a bowel screening procedure for the user), information concerning the bowel screening procedure for the user (e.g., a timing of the bowel screening procedure), and/or the like.
  • a bowel preparation agent prescribed for the user e.g., to cleanse the bowel of the user for a bowel screening procedure for the user
  • information concerning the bowel screening procedure for the user e.g., a timing of the bowel screening procedure
  • the user device may obtain consumption information concerning consumption of the bowel preparation agent by the user.
  • the user may interact, via the user interface of the user device, with the one or more applications running on the user device to enter the consumption information into the user device.
  • the user device may communicate with a different device, such as a server device, to obtain the consumption information.
  • the consumption information may include information concerning a dosage of the bowel preparation agent, information concerning an amount of bowel preparation agent consumed by the user, information concerning an amount of time since the amount of bowel preparation agent was consumed by the user, information concerning a total amount of bowel preparation agent consumed by the user, information concerning a time of an initial consumption of the bowel preparation agent by the user, and/or the like.
  • the user device may send the user information and/or the consumption information to the analyzing platform.
  • the analyzing platform may obtain the user information and/or the consumption information from the user device. Additionally, or alternatively, the analyzing platform may communicate with a different device, such as a server device, to obtain the user information and/or the consumption information.
  • the user device may display, on a display of the user device, a first instruction regarding capturing an image of a liquid in a receptacle.
  • the one or more applications may instruct a user to position the user device over the receptacle for the user device to capture an image of the liquid in the receptacle.
  • the receptacle may be a container, such as a bottle, a sample tube, and/or the like. Additionally, or alternatively, the receptacle may be a toilet, a bedpan, and/or the like.
  • the liquid may be water (e g., water in a toilet), a chemical solution (e.g., a saline solution, a deodonzing solution, a solution with a colored dye, and/or the like), and/or the like.
  • a chemical solution e.g., a saline solution, a deodonzing solution, a solution with a colored dye, and/or the like
  • the user device may obtain a first image of the liquid in the receptacle.
  • the user may point the camera device of the user device at the liquid in the receptacle and/or the camera device of the user device may automatically capture the first image.
  • the user may point the camera device of the user device at the liquid and/or the user may interact, via the user interface of the user device, with the one or more applications running on the user device (e.g., to select an option to capture an image) to cause the camera device to capture the first image.
  • the first image may include image data associated with a particular spectral range (e.g., an image associated with red light, green light, blue light, visible light, infrared light, ultraviolet light, and/or the like).
  • the user device may cause the display of the user device to display the first image after the user device captures the first image.
  • the user device may send the first image to the analyzing platform.
  • the analyzing platform may obtain the first image from the user device.
  • the analyzing platform may determine a set of characteristics (e.g., visual characteristics) concerning the liquid.
  • the set of characteristics may include a color associated with the liquid; a light intensity associated with the liquid; a brightness associated with the liquid; a spectral feature (e.g., a visible spectral feature, a near-infrared spectral feature, and/or the like), a biochemical feature, a molecular feature, and/or the like of the liquid, and/or the like.
  • the analyzing platform may analyze and/or process (e.g., using one or more image analyzing techniques and/or one or more image processing techniques) the first image to determine the set of characteristics.
  • the analyzing platform may determine a color associated with the liquid by processing the first image using a color normalization technique.
  • the analyzing platform may analyze the first image, after color normalizing the first image, to determine a light intensity associated with the liquid, a brightness associated with the liquid, and/or the like.
  • the analyzing platform may determine an area of the first image associated with the liquid (e.g., using an object recognition technique) and may analyze and/or process image data of the first image associated with the area (e.g., only analyze and/or process image data associated with the area and not image data associated with the rest of the first image) to determine the set of characteristics.
  • the user after the user device obtains the first image, may deposit a rectal sample (e.g., rectal effluent, rectal discharge, stool, and/or the like) in the liquid in the receptacle (e.g., the user may evacuate the rectal sample from the bowel of the user into the receptacle).
  • the rectal sample may be diluted in the receptacle (e.g., the rectal sample may be mixed with the liquid in the receptacle, such as water in a toilet).
  • the user, the user device, another device, and/or the like may deposit a reagent (e.g., a reactant, a solvent, a catalyst, and/or the like) in the receptacle with the rectal sample (e.g., to cause a chemical reaction associated with the rectal sample).
  • a reagent e.g., a reactant, a solvent, a catalyst, and/or the like
  • the user device may display a second instruction regarding capturing an image of the rectal sample (e.g., of the user) in the liquid in the receptacle in a similar manner as described herein in relation to Fig. IB.
  • the one or more applications may instruct the user to position the user device over the receptacle for the user device to capture an image of the rectal sample in the liquid in the receptacle.
  • the user device may obtain a second image of the rectal sample in the receptacle in a similar manner as described herein in relation to Fig. IB.
  • the user may point the camera device of the user device at the rectal sample in the liquid in the receptacle and/or the camera device of the user device may automatically capture the second image.
  • the user may point the camera device of the user device at the rectal sample and/or the user may interact, via the user interface of the user device, with the one or more applications running on the user device (e.g., to select an option to capture an image) to cause the camera device to capture the second image.
  • the user device may cause the display of the user device to display the second image after the user device captures the second image.
  • the second image may include image data associated with a particular spectral range (e.g., an image associated with red light, green light, blue light, visible light, infrared light, ultraviolet light, and/or the like).
  • the user device may cause the display of the user device to display the second image after the user device captures the second image.
  • the user device may send the second image to the analyzing platform in a similar manner as described herein in relation to Fig. IB.
  • the analyzing platform may obtain the second image from the user device.
  • the analyzing platform may determine a set of characteristics (e.g., visual characteristics) concerning the rectal sample in a similar manner as described herein in relation to Fig. IB.
  • the set of characteristics may include a color associated with the rectal sample; a light intensity associated with the rectal sample; a brightness associated with the rectal sample; a spectral feature (e.g., a visible spectral feature, a near-infrared spectral feature, and/or the like), a biochemical feature, a molecular feature, and/or the like of the liquid; a shape of the rectal sample; and/or the like.
  • the analyzing platform may analyze and/or process (e.g., using one or more image analyzing techniques and/or one or more image processing techniques) the second image to determine the set of characteristics. For example, the analyzing platform may determine a color associated with the rectal sample by processing the second image using a color normalization technique. The analyzing platform may analyze the second image, after color normalizing the second image, to determine a light intensity associated with the rectal sample, a brightness associated with the rectal sample, and/or the like.
  • the analyzing platform may determine an area of the second image associated with the rectal sample (e.g., using an object recognition technique) and may analyze and/or process image data of the second image associated with the area (e.g., only process image data associated with the area and not image data associated with the rest of the first image) to determine the set of characteristics.
  • the analyzing platform may determine one or more estimated biochemical measurements associated with the rectal sample.
  • the one or more biochemical measurements may include an estimated hemoglobin measurement associated with the rectal sample (e.g., an estimated amount of hemoglobin in the rectal sample); an estimated protein measurement associated with the rectal sample (e.g., an estimated amount of protein in the rectal sample); an estimated fat measurement associated with the rectal sample (e.g., an estimated amount of fat in the rectal sample); an estimated carbohydrate measurement associated with the rectal sample (e.g., an estimated amount of carbohydrate in the rectal sample); an estimated nucleic acid measurement associated with the rectal sample (e.g., an estimated amount of nucleic acid in the rectal sample); an estimated acidity measurement associated with the rectal sample (e.g., an estimated pH value of the rectal sample); and/or the like.
  • an estimated hemoglobin measurement associated with the rectal sample e.g., an estimated amount of hemoglobin in the rectal sample
  • the analyzing platform may determine the one or more estimated biochemical measurements associated with the rectal sample based on the set of characteristics of the liquid (hereinafter the“first set of characteristics”) and/or the set of
  • the analyzing platform may compare one or more elements of the first set of characteristics (e.g., the color associated with the liquid, light intensity associated with the liquid, the brightness associated with the liquid, and/or the like) and corresponding one or more elements of the second set of characteristics (e.g., the color associated with the rectal sample, the light intensity associated with the rectal sample, the brightness associated with the rectal sample, and/or the like) to determine the one or more estimated biochemical measurements.
  • the analyzing platform may compare the color associated with the liquid and the color associated with the rectal sample and/or may use a colorimetric processing technique to determine the one or more estimated biochemical measurements.
  • the analyzing platform may utilize one or more first models (e.g., one or more machine learning models) to process and/or analyze the first set of characteristics and/or the second set of characteristics to determine the one or more estimated biochemical measurements associated with the rectal sample.
  • the analyzing platform may train a first model (e.g., one of the one or more first models, each of the one or more first models, and/or the like) based on historical data (e.g., historical information concerning first sets of characteristics, historical information concerning second sets of characteristics, historical information concerning estimated biochemical measurements, and/or the like).
  • the analyzing platform may separate the historical data into a training set, a validation set, a test set, and/or the like.
  • the training set may be utilized to train the first model.
  • the validation set may be utilized to validate results of the trained first model.
  • the test set may be utilized to test operation of the first model.
  • the analyzing platform may train the first model using, for example, an unsupervised training procedure and based on the historical data. For example, the analyzing platform may perform dimensionality reduction to reduce the historical data to a minimum feature set, thereby reducing resources (e g., processing resources, memory resources, and/or the like) to train the first model, and may apply a classification technique to the minimum feature set.
  • resources e g., processing resources, memory resources, and/or the like
  • the analyzing platform may use a logistic regression classification technique to determine a categorical outcome. Additionally, or alternatively, the analyzing platform may use a naive Bayesian classifier technique. In this case, the analyzing platform may perform binary recursive partitioning to split the historical data into partitions and/or branches and use the partitions and/or branches to determine outcomes. Based on using recursive partitioning, the analyzing platform may reduce utilization of computing resources relative to manual, linear sorting and analysis of data points, thereby enabling use of thousands, millions, or billions of data points to train the first model, which may result in a more accurate model than using fewer data points.
  • the analyzing platform may use a support vector machine (SVM) classifier technique to generate a non-linear boundary between data points in the training set.
  • SVM support vector machine
  • the non-linear boundary is used to classify test data into a particular class.
  • the analyzing platform may train the first model using a supervised training procedure that includes receiving input to the first model from a subject matter expert, which may reduce an amount of time, an amount of processing resources, and/or the like to train the first model relative to an unsupervised training procedure.
  • the analyzing platform may use one or more other model training techniques, such as a neural network technique, a latent semantic indexing technique, and/or the like.
  • the analyzing platform may perform an artificial neural network processing technique (e.g., using a two-layer feedforward neural network architecture, a three-layer feedforward neural network architecture, and/or the like) to perform pattern recognition with regard to patterns of the historical data.
  • using the artificial neural network processing technique may improve an accuracy of the trained first model generated by the analyzing platform by being more robust to noisy, imprecise, or incomplete data, and by enabling the analyzing platform to detect patterns and/or trends undetectable to human analysts or systems using less complex techniques.
  • the analyzing platform may receive a trained first model from another device (e.g., a server device).
  • the other device may generate the first model based on having trained the first model in a manner similar to that described above, and may provide the trained first model to the analyzing platform (e.g., may pre-load the analyzing platform with the trained first model, may receive a request from the analyzing platform for the first trained model, and/or the like).
  • the analyzing platform may determine information concerning estimated bowel cleanliness of the user (e.g., to assist in determining whether a bowel of the user is sufficiently clean to undergo a bowel screening procedure).
  • the information concerning estimated bowel cleanliness may indicate an estimated degree of bowel visualization (e.g., based on a bowel cleanliness rating scale, such as the Boston Bowel Preparation Scale (BBPS)).
  • BBPS Boston Bowel Preparation Scale
  • the analyzing platform may determine the information concerning estimated bowel cleanliness based on a turbidity score of the rectal sample (e.g., that includes rectal effluent).
  • the turbidity score may indicate a measure of turbidity of the rectal sample (e.g., a relative clarity of the rectal sample).
  • a high turbidity score may indicate that the rectal sample has high turbidity
  • a low turbidity score may indicate that the rectal sample has low turbidity, and/or the like.
  • the analyzing platform may determine the turbidity score based on the first set of characteristics and/or the second set of characteristics.
  • the analyzing platform may compare one or more elements of the first set of characteristics (e.g., the color associated with the liquid, the light intensity associated with the liquid, the brightness associated with the liquid, and/or the like) and corresponding one or more elements of the second set of characteristics (e.g ., the color associated with the rectal sample, the light intensity associated with the rectal sample, the brightness associated with the rectal sample, and/or the like) to determine the turbidity score.
  • the first set of characteristics e.g., the color associated with the liquid, the light intensity associated with the liquid, the brightness associated with the liquid, and/or the like
  • the second set of characteristics e.g., the color associated with the rectal sample, the light intensity associated with the rectal sample, the brightness associated with the rectal sample, and/or the like
  • the analyzing platform may compare the light intensity associated with the liquid (e.g., after color normalizing the first image) and the light intensity associated with the rectal sample (e.g., after color normalizing the second image) to determine a light intensity value (e.g., a difference in the light intensity associated with the liquid and the light intensity associated with the rectal sample).
  • the analyzing platform may determine the turbidity score based on the light intensity value (e.g., based on a known relationship, such a linear relationship, an exponential relationship, an inverse relationship, and/or the like, between turbidity scores and light intensity values).
  • the analyzing platform may utilize one or more second models (e.g., one or more machine learning models) to process and/or analyze the first set of characteristics and/or the second set of characteristics to determine the turbidity score.
  • the analyzing platform may receive, generate, and/or train the second model in a similar manner as described herein in relation to the first model.
  • the analyzing platform may train a second model (e.g., one of the one or more second models, each of the one or more second models, and/or the like) based on historical data (e.g., historical information concerning first sets of characteristics, historical information concerning second sets of characteristics, historical information concerning turbidity scores, and/or the like).
  • the analyzing platform may perform a set of data manipulation procedures, perform a training operation, use a classification technique, perform a recursive feature elimination procedure, and/or the like as described herein to determine an association between a first set of characteristics, a second set of characteristics, and/or a turbidity score.
  • the analyzing platform may determine the information concerning estimated bowel cleanliness based on the turbidity score of the rectal sample, as well as the user information, the consumption information, and/or the like. For example, the analyzing platform may determine the information concerning estimated bowel cleanliness based on the age of the user, the health status of the user, the information concerning the amount of bowel preparation agent consumed by the user, the information concerning the time of consumption of the amount of bowel preparation agent consumed by the user, and/or the turbidity score.
  • the analyzing platform may utilize one or more third models (e.g., one or more machine learning models) to process and/or analyze the user information, the consumption information, the turbidity score, and/or the like to determine the information concerning estimated bowel cleanliness.
  • the analyzing platform may receive, generate, and/or train a third model in a similar manner as described herein in relation to the first model and/or the second model.
  • the analyzing platform may train a third model (e.g., one of the one or more third models, each of the one or more third models, and/or the like) based on historical data (e.g., historical user information, historical consumption information, historical turbidity scores, and/or the like).
  • the analyzing platform may perform a set of data manipulation procedures, perform a training operation, use a classification technique, perform a recursive feature elimination procedure, and/or the like as described herein to determine an association between user information, consumption information, a turbidity score, and/or information concerning estimated bowel cleanliness.
  • the analyzing platform may send rectal sample information to the user device.
  • the rectal sample information may include the one or more estimated biochemical measurements associated with the rectal sample, the turbidity score, the information concerning estimated bowel cleanliness, and/or the like.
  • the user device may obtain the rectal sample information from the analyzing platform.
  • the analyzing platform and/or the user device may cause one or more actions. For example, the user device and/or the analyzing platform may cause at least one estimated biochemical measurement, of the one or more estimated biochemical measurements associated with the rectal sample, to be displayed on a display of the user device.
  • the user device and/or analyzing platform may determine that an estimated biochemical measurement is outside a normal range (e.g., the estimated biochemical measurement is less than a normal minimum measurement or greater than a normal maximum measurement).
  • the user device and/or the analyzing platform may determine, based on determining that the estimated biochemical measure is outside the normal range, an estimated health condition of the user (e.g., that indicates whether the user has a gastrointestinal disease, whether the user is at risk of developing a gastrointestinal disease, whether the user is anemic, whether the user is dehydrated, and/or the like).
  • the user device and/or the analyzing platform may cause, based on the estimated health condition of the user, a different device, such as a server device, to schedule an appointment time for a bowel screening procedure, a blood test, a physical examination (e.g., by a doctor), and/or the like.
  • a different device such as a server device, to schedule an appointment time for a bowel screening procedure, a blood test, a physical examination (e.g., by a doctor), and/or the like.
  • the analyzing platform may receive information concerning one or more biochemical measurements from a different device (e.g., a laboratory technician may send, using the different device, information concerning blood test results of the user to the analyzing platform).
  • the analyzing platform may cause the first model to be updated based on the first image, the second image, the user information, the one or more estimated biochemical measurement, and/or the information concerning one or more biochemical measurements.
  • the user device may generate one or more instructions concerning consumption of a bowel preparation agent (e.g., for a bowel screening procedure) by the user and cause the user device to display the one or more instructions on the display of the user device.
  • the one or more instructions may indicate that the user is to stop consuming the bowel preparation agent, that the user is to take a particular amount of the bowel preparation agent at a particular time, that the user is to contact a medical professional (e.g., a doctor, a nurse, and/or the like) about consumption of the bowel preparation agent, and/or the like.
  • the user device may determine a dose of the bowel preparation agent to be consumed by the user, determine a time the dose is to be consumed by the user, and cause the user device to display information concerning the dose and the time on a display of the user device.
  • the user device and/or the analyzing platform may determine a time range for commencing a bowel screening procedure for the user based on the user information, the consumption information, the one or more estimated biochemical measurements associated with the rectal sample, the turbidity score, and/or the information concerning estimated bowel cleanliness of the user.
  • the user device may generate a message that includes the time range and send the message to a different device, such as a server device, to cause the different device to schedule an appointment time concerning the bowel screening procedure.
  • a server device such as a server device
  • the user device may initiate a communication session with a communication device associated with a bowel screening procedure for the user (e.g., the user device may automatically call a communication device associated with a healthcare facility associated with the bowel screen procedure) to allow the user of the user device to communicate with a representative to schedule an appointment time concerning the bowel screening procedure.
  • a communication device associated with a bowel screening procedure for the user (e.g., the user device may automatically call a communication device associated with a healthcare facility associated with the bowel screen procedure) to allow the user of the user device to communicate with a representative to schedule an appointment time concerning the bowel screening procedure.
  • the analyzing platform may receive information concerning turbidity of effluent in the bowel of the user from a different device (e.g., an endoscopist may collect and analyze effluent from the bowel of the user during the bowel screening procedure and send, using the different device, information concerning turbidity of the effluent to the analyzing platform).
  • the analyzing platform may cause the second model to be updated based on the first image, the second image, the user information, the consumption information, the turbidity score, and/or the information concerning turbidity of effluent in the bowel of the user.
  • the user device may receive information concerning actual bowel cleanliness of the user from a different device (e.g., an endoscopist may grade the cleanliness of the bowel of the user during the bowel screening procedure and send, using the different device, information concerning actual bowel cleanliness of the user to the analyzing platform).
  • the analyzing platform may cause the third model to be updated based on the first image, the second image, the user information, the consumption information, the turbidity score, the information concerning estimated bowel cleanliness of the user, and/or the information concerning actual bowel cleanliness of the user
  • the analyzing platform may receive feedback from the user of the user device (e.g., the user may enter feedback into the user device after the bowel screening procedure, and/or the user may use another device to enter the feedback, and send the feedback to the analyzing platform).
  • the feedback may concern the bowel preparation agent, consumption of the bowel preparation agent, the bowel screening procedure, and/or the like.
  • the analyzing platform may cause the second model and/or the third model to be updated based on the feedback.
  • Some example implementations described herein concern the user device and/or the analyzing platform obtaining and analyzing a first image and a second image to determine rectal sample information.
  • implementations include the user device and/or the analyzing platform obtaining and analyzing multiple images, in a similar manner as described herein, to determine the rectal sample information.
  • Some example implementations described herein concern the analyzing platform performing one or more functions (e.g., determining the set of characteristics concerning the liquid, determining the set of characteristics concerning the rectal sample, determining the one or more estimated biochemical measurements associated with the rectal sample, determining the turbidity score, determining the information concerning estimated bowel cleanliness of the user, causing the one or more actions to be performed, and/or the like), but some implementations include the user device performing at least one function of the one or more functions. For example, in some implementations, the user device may not communicate with the analyzing platform and may perform all of the one or more functions.
  • some example implementations described herein concern the user device performing one or more additional functions (e.g., obtaining the user information, obtaining the consumption information, generating and/or causing display of messages, causing the one or more actions to be performed, and/or the like), but some
  • implementations include the analyzing platform performing at least one additional function of the one or more additional functions.
  • Some example implementations described herein concern the analyzing platform performing and/or the user device determining one or more estimated biochemical measurements associated with a rectal sample, determining a turbidity score associated with the rectal sample, and/or the like.
  • contemplated implementations include the analyzing platform and/or the user device determining one or more estimated biochemical measurements associated with other bodily fluids (e.g., urine, sputum, mucus, and/or the like), determining a turbidity score associated with other bodily fluids, and/or the like.
  • a turbidity score associated with urine may indicate a measure of specific gravity of a user’s urine.
  • the analyzing platform and/or the user device may determine, based on the one or more estimated biochemical measurements and/or the turbidity score associated with the urine, sputum, mucus, and/or the like, information concerning an estimated indicator of health of the user. For example, the analyzing platform and/or user device may determine, based on the one or more estimated biochemical measurements and/or the turbidity score associated with the urine, information concerning an estimated hydration status of the user and/or information concerning estimated kidney function of the user in a similar manner as described herein.
  • Figs. 1A- ID are provided merely as examples. Other examples may differ from what is described with regard to Figs. 1A-1D.
  • FIG. 2 is a diagram of an example environment 200 in which systems and/or methods described herein may be implemented.
  • environment 200 may include a user device 210, a network 220, an analyzing platform 230 in a cloud computing environment 232 that includes computing resources 234, and/or the like.
  • Devices of environment 200 may interconnect via wired connections, wireless connections, or a combination of wired and wireless connections.
  • User device 210 includes one or more devices capable of receiving, generating, storing, processing, analyzing, and/or providing information, such as information described herein.
  • user device 210 may include a computer (e.g., a desktop computer, a laptop computer, a tablet computer, a handheld computer, a server device, etc.), a mobile phone (e.g., a smart phone, a radiotelephone, etc.), an internet of things (IoT) device or smart appliance, or a similar device.
  • User device 210 may include a camera device and may be configured to capture an image using the camera device.
  • the camera device may be configured to capture hyperspectral images and may include a filter that is configured to allow the camera device to capture images associated with a particular spectral range.
  • user device 210 may receive information from and/or transmit information to analyzing platform 230, and/or the like.
  • Network 220 includes one or more wired and/or wireless networks.
  • network 220 may include a cellular network (e.g., a long-term evolution (LTE) network, a code division multiple access (CDMA) network, a 3G network, a 4G network, a 5G network, another type of next generation network, etc.), a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a telephone network (e.g., the Public Switched Telephone Network (PSTN)), a private network, an ad hoc network, an intranet, the internet, a fiber optic-based network, a cloud computing network, a mesh network and/or the like, and/or a combination of these or other types of networks.
  • LTE long-term evolution
  • CDMA code division multiple access
  • 3G Third Generation
  • 4G fourth generation
  • 5G Fifth Generation
  • PLMN public land mobile network
  • PLMN public land mobile network
  • Analyzing platform 230 includes one or more devices capable of determining one or more estimated biochemical measurements associated with a rectal sample, determining a turbidity score of the rectal sample, and/or determining information concerning estimated bowel cleanliness of a user.
  • analyzing platform 230 may be designed to be modular such that certain software components may be swapped in or out depending on a particular need. As such, analyzing platform 230 may be easily and/or quickly reconfigured for different uses. In some implementations, analyzing platform 230 may receive information from and/or transmit information to user device 210, such as via network 220.
  • analyzing platform 230 may be hosted in a cloud computing environment 232.
  • analyzing platform 230 may be non-cloud-based (i.e., may be implemented outside of a cloud computing environment) or may be partially cloud-based.
  • Cloud computing environment 232 includes an environment that hosts analyzing platform 230.
  • Cloud computing environment 232 may provide computation, software, data access, storage, etc. services that do not require end-user knowledge of a physical location and configuration of system(s) and/or device(s) that hosts analyzing platform 230.
  • cloud computing environment 232 may include a group of computing resources 234 (referred to collectively as“computing resources 234” and individually as“computing resource 234”).
  • Computing resource 234 includes one or more personal computers, workstation computers, server devices, or other types of computation and/or communication devices.
  • computing resource 234 may host analyzing platform 230.
  • the cloud resources may include compute instances executing in computing resource 234, storage devices provided in computing resource 234, data transfer devices provided by computing resource 234, etc.
  • computing resource 234 may communicate with other computing resources 234 via wired connections, wireless connections, or a combination of wired and wireless connections.
  • computing resource 234 includes a group of cloud resources, such as one or more applications (“APPs”) 234-1, one or more virtual machines (“VMs”) 234-2, virtualized storage (“VSs”) 234-3, one or more hypervisors (“HYPs”) 234-4, and/or the like.
  • APPs applications
  • VMs virtual machines
  • VSs virtualized storage
  • HOPs hypervisors
  • Application 234-1 includes one or more software applications that may be provided to or accessed by user device 210. Application 234-1 may eliminate a need to install and execute the software applications on user device 210.
  • application 234-1 may include software associated with analyzing platform 230 and or any other software capable of being provided via cloud computing environment 232.
  • one application 234-1 may send/receive information to/from one or more other applications 234-1, via virtual machine 234-2.
  • Virtual machine 234-2 includes a software implementation of a machine (e.g ., a computer) that executes programs like a physical machine.
  • Virtual machine 234-2 may be either a system virtual machine or a process virtual machine, depending upon use and degree of
  • a system virtual machine may provide a complete system platform that supports execution of a complete operating system (“OS”).
  • a process virtual machine may execute a single program, and may support a single process.
  • virtual machine 234-2 may execute on behalf of a user (e g., a user of user device 210), and may manage infrastructure of cloud computing environment 232, such as data management, synchronization, or long -duration data transfers.
  • Virtualized storage 234-3 includes one or more storage systems and/or one or more devices that use virtualization techniques within the storage systems or devices of computing resource 234.
  • types of virtualizations may include block virtualization and file virtualization.
  • Block virtualization may refer to abstraction (or separation) of logical storage from physical storage so that the storage system may be accessed without regard to physical storage or heterogeneous structure. The separation may permit administrators of the storage system flexibility in how the administrators manage storage for end users.
  • File virtualization may eliminate dependencies between data accessed at a file level and a location where files are physically stored. This may enable optimization of storage use, server consolidation, and/or performance of non-disruptive file migrations.
  • Hypervisor 234-4 may provide hardware virtualization techniques that allow multiple operating systems (e.g.,“guest operating systems”) to execute concurrently on a host computer, such as computing resource 234. Hypervisor 234-4 may present a virtual operating platform to the guest operating systems, and may manage the execution of the guest operating systems. Multiple instances of a variety of operating systems may share virtualized hardware resources.
  • multiple operating systems e.g.,“guest operating systems”
  • Hypervisor 234-4 may present a virtual operating platform to the guest operating systems, and may manage the execution of the guest operating systems. Multiple instances of a variety of operating systems may share virtualized hardware resources.
  • the number and arrangement of devices and networks shown in Fig. 2 are provided as one or more examples. In practice, there may be additional devices and/or networks, fewer devices and/or networks, different devices and/or networks, or differently arranged devices and/or networks than those shown in Fig. 2. Furthermore, two or more devices shown in Fig. 2 may be implemented within a single device, or a single device shown in Fig. 2 may be implemented as multiple, distributed devices. Additionally, or alternatively, a set of devices (e.g., one or more devices) of environment 200 may perform one or more functions described as being performed by another set of devices of environment 200.
  • Fig. 3 is a diagram of example components of a device 300.
  • Device 300 may correspond to user device 210, analyzing platform 230, computing resource 234, and/orthe like.
  • user device 210, analyzing platform 230, computing resource 234, and/or the like may include one or more devices 300 and/or one or more components of device 300.
  • device 300 may include a bus 310, a processor 320, a memory 330, a storage component 340, an input component 350, an output component 360, and a communication interface 370.
  • Bus 310 includes a component that permits communication among multiple components of device 300.
  • Processor 320 is implemented in hardware, firmware, and/or a combination of hardware and software.
  • Processor 320 is a central processing unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), a microprocessor, a microcontroller, a digital signal processor (DSP), a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or another type of processing component.
  • processor 320 includes one or more processors capable of being programmed to perform a function.
  • Memory 330 includes a random access memory (RAM), a read only memory (ROM), and/or another type of dynamic or static storage device (e.g., a flash memory, a magnetic memory, and/or an optical memory) that stores information and/or instructions for use by processor 320.
  • RAM random access memory
  • ROM read only memory
  • static storage device e.g., a flash memory, a magnetic memory, and/or an optical memory
  • Storage component 340 stores information and/or software related to the operation and use of device 300.
  • storage component 340 may include a hard disk (e.g., a magnetic disk, an optical disk, and/or a magneto-optic disk), a solid state drive (SSD), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and/or another type of non- transitory computer-readable medium, along with a corresponding drive.
  • Input component 350 includes a component that permits device 300 to receive information, such as via user input (e.g., a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, and/or a microphone). Additionally, or alternatively, input component 350 may include a component for determining location (e.g., a global positioning system (GPS) component) and/or a sensor (e.g., an accelerometer, a gyroscope, an actuator, another type of positional or environmental sensor, and/or the like).
  • Output component 360 includes a component that provides output information from device 300 (via, e.g., a display, a speaker, a haptic feedback component, an audio or visual indicator, and/or the like).
  • Communication interface 370 includes a transceiver-like component (e.g., a transceiver, a separate receiver, a separate transmitter, and/or the like) that enables device 300 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections.
  • Communication interface 370 may permit device 300 to receive information from another device and/or provide information to another device.
  • communication interface 370 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, and/or the like.
  • RF radio frequency
  • USB universal serial bus
  • Device 300 may perform one or more processes described herein. Device 300 may perform these processes based on processor 320 executing software instructions stored by a non- transitory computer-readable medium, such as memory 330 and/or storage component 340.
  • a non-transitory computer-readable medium such as memory 330 and/or storage component 340.
  • the term“computer-readable medium” refers to a non-transitory memory device.
  • a memory device includes memory space within a single physical storage device or memory space spread across multiple physical storage devices.
  • Software instructions may be read into memory 330 and/or storage component 340 from another computer-readable medium or from another device via communication interface 370. When executed, software instructions stored in memory 330 and/or storage component 340 may cause processor 320 to perform one or more processes described herein. Additionally, or alternatively, hardware circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Thus, implementations described herein are not limited to any specific combination of hardware circuitry and software.
  • device 300 may include additional components, fewer components, different components, or differently arranged components than those shown in Fig. 3. Additionally, or alternatively, a set of components (e.g., one or more components) of device 300 may perform one or more functions described as being performed by another set of components of device 300.
  • a set of components e.g., one or more components
  • Fig. 4 is a flow chart of an example process 400 for analyzing image data to determine rectal sample information.
  • one or more process blocks of Fig. 4 may be performed by a user device (e.g., user device 210).
  • one or more process blocks of Fig. 4 may be performed by another device or a group of devices separate from or including the user device, such as analyzing platform 230, and/or the like.
  • process 400 may include obtaining a first image of a liquid in a receptacle (block 410).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 400 may include analyzing the first image to determine a first set of visual characteristics concerning the liquid (block 420).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 400 may include obtaining a second image of a rectal sample in the liquid in the receptacle, wherein the rectal sample originated from a bowel of a subject (block 430).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • the rectal sample originated from a bowel of a subject.
  • process 400 may include analyzing the second image to determine a second set of visual characteristics concerning the rectal sample (block 440).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 400 may include determining, based on the first set of visual characteristics and the second set of visual characteristics, rectal sample information (block 450).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 400 may include causing one or more actions to be performed based on the rectal sample information (block 460).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • Process 400 may include additional implementations, such as any single implementation or any combination of implementations described below and/or in connection with one or more other processes described elsewhere herein.
  • the rectal sample information includes at least one of one or more estimated biochemical measurements associated with the rectal sample; a turbidity score of the rectal sample; or information concerning estimated bowel cleanliness of the bowel of the subject.
  • the one or more estimated biochemical measurements associated with the rectal sample include at least one of an estimated hemoglobin measurement associated with the rectal sample; an estimated protein measurement associated with the rectal sample; an estimated fat measurement associated with the rectal sample; an estimated carbohydrate measurement associated with the rectal sample; an estimated nucleic acid measurement associated with the rectal sample; or an estimated acidity measurement associated with the rectal sample.
  • analyzing the first image to determine the first set of visual characteristics further comprises determining a first area of the first image associated with the liquid, and analyzing image data of the first image associated with the first area to determine a light intensity and a color associated with the liquid
  • analyzing the second image to determine the second set of visual characteristics further comprises determining a second area of the second image associated with the rectal sample in the liquid, and analyzing image data of the second image associated with the second area to determine a light intensity and a color associated with the rectal sample.
  • the rectal sample information includes information concerning estimated bowel cleanliness of the bowel of the subject
  • determining the rectal sample information comprises determining, using at least one machine learning model and based on the first set of visual characteristics and the second set of visual characteristics, a turbidity score for the rectal sample that indicates a measure of turbidity of the rectal sample, and determining, using the at least one machine learning model and based on the turbidity score, the information concerning the estimated bowel cleanliness of the bowel of the subject.
  • the at least one machine learning model has been trained to determine the turbidity score based on a light intensity and a color associated with a particular liquid and a light intensity and a color associated with a particular rectal sample.
  • the additional machine learning model has been trained to determine the information concerning the estimated bowel cleanliness of the bowel of the subject based on at least one of: the turbidity score; an age of the subject; a sex of the subject; a health status of the subject; a health history of the subject; information concerning medication consumed by the subject;
  • information concerning an amount of bowel preparation agent consumed by the subject information concerning a dosage of the bowel preparation agent; information concerning an amount of time since the amount of bowel preparation agent was consumed by the subject; information concerning a total amount of bowel preparation agent consumed by the subject; or information concerning a time of an initial consumption of the bowel preparation agent by the subject.
  • determining the rectal sample information comprises: determining, using a machine learning model and based on the first set of visual characteristics and the second set of visual characteristics, one or more estimated biochemical measurements associated with the rectal sample.
  • the rectal sample information includes one or more estimated biochemical measurements associated with the rectal sample
  • determining the rectal sample information comprises: determining, using a colorimetric processing technique and based on the first set of visual characteristics and the second set of visual characteristics, the one or more estimated biochemical measurements associated with the rectal sample.
  • causing the one or more actions to be performed comprises: generating one or more instructions concerning consumption of a bowel preparation agent by the subject, and causing a user device to display the one or more instructions on a display of the user device.
  • causing the one or more actions to be performed comprises: determining, based on the rectal sample information, a time range for commencing a bowel screening procedure for the subject; generating a message that includes the time range, and sending the message to a different device to cause the different device to schedule an appointment time concerning the bowel screening procedure.
  • process 400 may include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in Fig. 4. Additionally, or alternatively, two or more of the blocks of process 400 may be performed in parallel.
  • Fig. 5 is a flow chart of an example process 500 for analyzing image data to determine rectal sample information.
  • one or more process blocks of Fig. 5 may be performed by an analyzing platform (e.g., analyzing platform 230).
  • one or more process blocks of Fig. 5 may be performed by another device or a group of devices separate from or including the device, such as a user device (e.g., user device 210), and/or the like..
  • process 500 may include obtaining, from a user device, a first image of a liquid in a receptacle (block 510).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 500 may include analyzing the first image to determine a characteristic associated with the liquid (block 520).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 500 may include obtaining, from the user device, a second image of a rectal sample in the liquid in the receptacle (block 530).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 500 may include analyzing the second image to determine a characteristic associated with the rectal sample (block 540).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 500 may include determining, using one or more machine learning models and based on the characteristic associated with the liquid and the characteristic associated with the rectal sample, rectal sample information (block 550).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 500 may include causing one or more actions to be performed based on the rectal sample information (block 560).
  • the analyzing platform e.g., using computing resource 234, processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • Process 500 may include additional implementations, such as any single implementation or any combination of implementations described below and/or in connection with one or more other processes described elsewhere herein.
  • the receptacle is a toilet and the liquid is water.
  • the characteristic associated with the liquid is a color associated with the liquid, a light intensity associated with the liquid, or a brightness associated with the liquid
  • the characteristic associated with the rectal sample is a color associated with the rectal sample, a light intensity associated with the rectal sample, or a brightness associated with the rectal sample.
  • analyzing the first image to determine the characteristic associated with the liquid includes processing the first image to color normalize the first image; and determining the characteristic associated with the liquid after processing the first image, and analyzing the second image to determine the characteristic associated with the rectal sample includes processing the second image to color normalize the second image, and determining the characteristic associated with the rectal sample after processing the second image.
  • causing the one or more actions to be performed includes receiving additional rectal sample information from a different device; and causing at least one machine learning model, of the one or more machine learning models, to be updated based on the additional rectal sample information.
  • process 500 may include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in Fig. 5. Additionally, or alternatively, two or more of the blocks of process 500 may be performed in parallel.
  • Fig. 6 is a flow chart of an example process 600 for analyzing image data to determine rectal sample information.
  • one or more process blocks of Fig. 6 may be performed by a user device (e.g., user device 210).
  • one or more process blocks of Fig. 6 may be performed by another device or a group of devices separate from or including the device, such as an analyzing platform (e.g., analyzing platform 230), and/or the like.
  • an analyzing platform e.g., analyzing platform 230
  • process 600 may include causing display, on a display of the user device, of a first instruction regarding capturing an image of a liquid in a receptacle (block 610).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include obtaining, after causing display of the first instruction, a first image of the liquid (block 620).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include analyzing the first image to determine a first set of characteristics concerning the liquid (block 630).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include causing display, on the display of the user device, of a second instruction regarding capturing an image of a rectal sample, of a user of the user device, in the liquid in the receptacle (block 640).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include obtaining, after causing display of the second instruction, a second image of the rectal sample (block 650).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include analyzing the second image to determine a second set of characteristics concerning the rectal sample (block 660).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include determining, based on the first set of characteristics and the second set of characteristics, rectal sample information (block 670).
  • the user device e.g., using processor 320, memory 330, storage component 340, input component 350, output component 360, communication interface 370 and/or the like
  • process 600 may include automatically performing one or more actions based on the rectal sample information (block 680).
  • the user device may automatically perform one or more actions based on the rectal sample information, as described above.
  • Process 600 may include additional implementations, such as any single implementation or any combination of implementations described below and/or in connection with one or more other processes described elsewhere herein.
  • a camera device of the user device is configured to obtain the first image of the liquid and the second image of the rectal sample, wherein the camera device is configured to capture hyperspectral images.
  • automatically performing the one or more actions includes initiating a communication session with a communication device associated with a bowel screening procedure for the user.
  • the rectal sample information includes one or more estimated biochemical measurements associated with the rectal sample
  • automatically performing the one or more actions includes determining, based on the one or more estimated biochemical measurements associated with the rectal sample, an estimated health condition of the user, and automatically causing, based on the estimated health condition of the user, a different device to schedule an appointment time for at least one of the following: a bowel screening procedure, a blood test, or a physical examination of the user.
  • process 600 may include additional blocks, fewer blocks, different blocks, or differently arranged blocks than those depicted in Fig. 6. Additionally, or alternatively, two or more of the blocks of process 600 may be performed in parallel.
  • the term“component” is intended to be broadly construed as hardware, firmware, and/or a combination of hardware and software.
  • a user interface may include a graphical user interface, a non-graphical user interface, a text-based user interface, and/or the like.
  • a user interface may provide information for display.
  • a user may interact with the information, such as by providing input via an input component of a device that provides the user interface for display.
  • a user interface may be configurable by a device and/or a user (e.g., a user may change the size of the user interface, information provided via the user interface, a position of information provided via the user interface, etc.).
  • a user interface may be pre-configured to a standard configuration, a specific configuration based on a type of device on which the user interface is displayed, and/or a set of configurations based on capabilities and/or specifications associated with a device on which the user interface is displayed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Pathology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Medicinal Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

L'invention concerne une plateforme d'analyse pouvant obtenir une première image d'un liquide dans un réceptacle. La plateforme d'analyse peut analyser la première image pour déterminer un premier ensemble de caractéristiques visuelles concernant le liquide. La plateforme d'analyse peut obtenir une deuxième image d'un échantillon rectal dans le liquide dans le récipient, l'échantillon rectal provenant d'un intestin d'un sujet. La plateforme d'analyse peut analyser la deuxième image pour déterminer un deuxième ensemble de caractéristiques visuelles concernant l'échantillon rectal. La plateforme d'analyse peut déterminer, sur la base du premier ensemble de caractéristiques visuelles et du deuxième ensemble de caractéristiques visuelles, des informations d'échantillon rectal. La plate-forme d'analyse peut provoquer la réalisation d'une ou de plusieurs actions sur la base des informations d'échantillon rectal.
PCT/US2020/018390 2019-02-18 2020-02-14 Analyse de données d'image pour déterminer des informations d'échantillon rectal Ceased WO2020172073A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/310,686 US12118725B2 (en) 2019-02-18 2020-02-14 Analyzing image data to determine bowel preparation quality

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201962807079P 2019-02-18 2019-02-18
US62/807,079 2019-02-18

Publications (1)

Publication Number Publication Date
WO2020172073A1 true WO2020172073A1 (fr) 2020-08-27

Family

ID=72144421

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2020/018390 Ceased WO2020172073A1 (fr) 2019-02-18 2020-02-14 Analyse de données d'image pour déterminer des informations d'échantillon rectal

Country Status (2)

Country Link
US (1) US12118725B2 (fr)
WO (1) WO2020172073A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115516310A (zh) * 2020-01-15 2022-12-23 黑暗峡谷实验室有限责任公司 用于评估结肠镜检查准备的系统和方法
WO2023064053A1 (fr) * 2021-10-15 2023-04-20 The Johns Hopkins University Détection de l'hémoglobine basée sur une caméra

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4004938A1 (fr) * 2019-07-31 2022-06-01 Dig Labs Corporation Évaluation de la santé d'un animal
US11763920B2 (en) 2019-07-31 2023-09-19 Dig Labs Corporation Mucus analysis for animal health assessments

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050261605A1 (en) * 2002-10-18 2005-11-24 S.A.E. Afikim Computerized Dairy Management System System for monitoring the health of an individual and method for use thereof
JP2010172498A (ja) * 2009-01-29 2010-08-12 Toto Ltd 尿温測定装置
KR20160046933A (ko) * 2014-10-20 2016-05-02 포항공과대학교 산학협력단 다중 형광 양자점-항체 복합체 프로브를 이용한 빠른 대장 내시경용 대장암 진단 방법
JP2018109597A (ja) * 2016-12-28 2018-07-12 サイマックス株式会社 健康モニタリングシステム、健康モニタリング方法および健康モニタリングプログラム
US20180317800A1 (en) * 2015-10-23 2018-11-08 The Regents Of The University Of California Characterizing gastrointestinal functions from surface electrophysiology recording

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102731877B1 (ko) * 2015-02-25 2024-11-21 아웃센스 다이아그나스틱스 엘티디. 신체 배출물 분석
US9689803B1 (en) * 2016-04-20 2017-06-27 Chroma Fish Corp. Method and system for measuring a colorimetric characteristic of a sample and calibration of same
JPWO2018008155A1 (ja) * 2016-07-08 2019-04-25 サイマックス株式会社 健康モニタリングシステム、健康モニタリング方法および健康モニタリングプログラム
JP2018096740A (ja) * 2016-12-09 2018-06-21 株式会社日立ハイテクノロジーズ 生体試料分析装置
WO2018187790A2 (fr) 2017-04-07 2018-10-11 Toi Labs, Inc. Dispositifs, procédés et systèmes de biosurveillance destinés à être utilisés dans un agencement de salle de bains

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050261605A1 (en) * 2002-10-18 2005-11-24 S.A.E. Afikim Computerized Dairy Management System System for monitoring the health of an individual and method for use thereof
JP2010172498A (ja) * 2009-01-29 2010-08-12 Toto Ltd 尿温測定装置
KR20160046933A (ko) * 2014-10-20 2016-05-02 포항공과대학교 산학협력단 다중 형광 양자점-항체 복합체 프로브를 이용한 빠른 대장 내시경용 대장암 진단 방법
US20180317800A1 (en) * 2015-10-23 2018-11-08 The Regents Of The University Of California Characterizing gastrointestinal functions from surface electrophysiology recording
JP2018109597A (ja) * 2016-12-28 2018-07-12 サイマックス株式会社 健康モニタリングシステム、健康モニタリング方法および健康モニタリングプログラム

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115516310A (zh) * 2020-01-15 2022-12-23 黑暗峡谷实验室有限责任公司 用于评估结肠镜检查准备的系统和方法
EP4090968A4 (fr) * 2020-01-15 2024-01-24 Dark Canyon Laboratories, LLC Systèmes et méthodes permettant d'évaluer une préparation à une coloscopie
WO2023064053A1 (fr) * 2021-10-15 2023-04-20 The Johns Hopkins University Détection de l'hémoglobine basée sur une caméra
US12306173B2 (en) 2021-10-15 2025-05-20 The Johns Hopkins University Camera-based hemoglobin detection

Also Published As

Publication number Publication date
US12118725B2 (en) 2024-10-15
US20220076418A1 (en) 2022-03-10

Similar Documents

Publication Publication Date Title
US12118725B2 (en) Analyzing image data to determine bowel preparation quality
Minaee et al. Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning
Nogueira-Rodríguez et al. Real-time polyp detection model using convolutional neural networks
Daich Varela et al. Artificial intelligence in retinal disease: clinical application, challenges, and future directions
He et al. Deployment of artificial intelligence in real-world practice: opportunity and challenge
KR101818074B1 (ko) 인공지능 기반 의료용 자동 진단 보조 방법 및 그 시스템
El Naqa et al. Lessons learned in transitioning to AI in the medical imaging of COVID-19
EP3489957A1 (fr) Plate-forme de prédiction de biomarqueur clinique accéléré (acbp)
CN109447985B (zh) 结肠镜图像分析方法、装置及可读存储介质
CN110728674A (zh) 图像处理方法及装置、电子设备和计算机可读存储介质
US20130282396A1 (en) System and method for deploying multiple clinical decision support models
JP2025176126A (ja) 人工知能基盤の血糖予測システムおよび方法
US11721023B1 (en) Distinguishing a disease state from a non-disease state in an image
Iqbal et al. AIM in Oncology
Yang et al. Use of artificial intelligence with retinal imaging in screening for diabetes-associated complications: systematic review
Kumar Saha et al. Mpox-XDE: an ensemble model utilizing deep CNN and explainable AI for monkeypox detection and classification
CN114708971A (zh) 一种风险评估方法及装置、存储介质及电子设备
WO2022261513A1 (fr) Procédés et systèmes de détection et de prédiction de maladie rénale chronique et de diabète de type 2 en utilisant des modèles d'apprentissage profond
US11145412B2 (en) Methods for the diagnosis and prognosis of melanoma from topical skin swabs
US11763944B2 (en) System and method for clinical decision support system with inquiry based on reinforcement learning
Liu et al. Dual-branch image projection network for geographic atrophy segmentation in retinal OCT images
US20240379225A1 (en) Determining a state of a medical condition based on a microbiome sample
JP2019149094A (ja) 診断支援システム、診断支援方法、及びプログラム
Chen Lung tumor diagnosis technology based on 6g wireless network sensors and big data analysis
KR101868744B1 (ko) 임상 진료 지침 제공 방법 및 이를 실행하는 프로그램이 기록된 기록 매체

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20758975

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20758975

Country of ref document: EP

Kind code of ref document: A1